{"id":{"repo_id":"iastate","oai_identifier":"oai:dr.lib.iastate.edu:20.500.12876/1wgeg5lr"},"canonical_url":"https://search.dev.ndltd.org/etd/iastate/oai:dr.lib.iastate.edu:20.500.12876/1wgeg5lr","repository":{"repo_id":"iastate","name":"Iowa State University","base_url":"https://dr.lib.iastate.edu/server/oai/request"},"display":{"title":"Communication-efficient personalization in federated learning for edge devices","abstract":"This dissertation advances practical, privacy-preserving federated learning under real-world constraints of heterogeneity, limited resources, and diverse data modalities. It develops algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb overfitting on heterogeneous clients, stabilize convergence, and lower both computation and communication during local updates. Next, we propose a multimodal federated framework with dual adapters: one larger adapter that is private to each client for personalization and a compact, shared adapter for knowledge transfer, augmented with selective pruning to balance local adaptation and global generalization for vision and language tasks. Then, we present a lightweight, convolution-based approach to time-series forecasting that pairs learnable trend/seasonality decomposition with an efficient federated protocol, enabling accurate prediction across distributed, streaming signals on constrained devices. Finally, we develop adaptive federated distillation with dual adapters and instance-wise fusion, aligning shared knowledge at the server while preserving client-specific representations to improve personalization under non-IID data. Together, these contributions chart a cohesive path toward scalable, resource-aware, and personalization friendly federated learning across data types and tasks, closing the gap between theoretical promise and deployment reality while maintaining user privacy.","abstract_html":"This dissertation advances practical, privacy-preserving federated learning under real-world constraints of heterogeneity, limited resources, and diverse data modalities. It develops algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb overfitting on heterogeneous clients, stabilize convergence, and lower both computation and communication during local updates. Next, we propose a multimodal federated framework with dual adapters: one larger adapter that is private to each client for personalization and a compact, shared adapter for knowledge transfer, augmented with selective pruning to balance local adaptation and global generalization for vision and language tasks. Then, we present a lightweight, convolution-based approach to time-series forecasting that pairs learnable trend/seasonality decomposition with an efficient federated protocol, enabling accurate prediction across distributed, streaming signals on constrained devices. Finally, we develop adaptive federated distillation with dual adapters and instance-wise fusion, aligning shared knowledge at the server while preserving client-specific representations to improve personalization under non-IID data. Together, these contributions chart a cohesive path toward scalable, resource-aware, and personalization friendly federated learning across data types and tasks, closing the gap between theoretical promise and deployment reality while maintaining user privacy.","abstract_has_math":false,"creators":["Nguyen, Duy Phuong"],"institution":"Iowa State University","degree_name":"Doctor of Philosophy","degree_level":"dissertation","degree_discipline":"Engineering","degree_department":"Department of Computer Science","school":null,"contributors":[],"advisors":["Jannesari, Ali","Basu, Samik","Huang, Xiaoqiu","Zhang, Wensheng","Gao, Hongyang"],"committee_chairs":[],"committee_members":[],"year":2025,"date_issued":"2025-12","date_published":"2025-12","updated_at":"2026-07-24T02:37:16Z","subjects":[],"languages":["en"],"rights":[],"rights_urls":[],"identifier_entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.31274/td-20260223-50"],"render_values":[{"text":"https://doi.org/10.31274/td-20260223-50","href":"https://doi.org/10.31274/td-20260223-50","code":true}]}]},"links":{"outbound_url":"https://dr.lib.iastate.edu/handle/20.500.12876/1wgeg5lr","outbound_label":"Repository record","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.advisor","label":"Advisor","values":["Jannesari, Ali","Basu, Samik","Huang, Xiaoqiu","Zhang, Wensheng","Gao, Hongyang"]},{"key":"dc:contributor.department","label":"Department","values":["Department of Computer Science"]},{"key":"dc:creator","label":"Author","values":["Nguyen, Duy Phuong"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2026-01-29T20:16:59Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2026-01-29T20:16:59Z"]},{"key":"dc:date.issued","label":"Date","values":["2025-12"]},{"key":"dc:type","label":"Dc Type","values":["dissertation"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Engineering"]},{"key":"thesis:degree_level","label":"Degree Level","values":["dissertation"]},{"key":"thesis:degree_name","label":"Degree Name","values":["Doctor of Philosophy"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Iowa State University"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language.iso","label":"Language (ISO)","values":["en"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.doi","label":"DOI","values":["https://doi.org/10.31274/td-20260223-50"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["https://dr.lib.iastate.edu/handle/20.500.12876/1wgeg5lr"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["This dissertation advances practical, privacy-preserving federated learning under real-world constraints of heterogeneity, limited resources, and diverse data modalities. It develops algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb overfitting on heterogeneous clients, stabilize convergence, and lower both computation and communication during local updates. Next, we propose a multimodal federated framework with dual adapters: one larger adapter that is private to each client for personalization and a compact, shared adapter for knowledge transfer, augmented with selective pruning to balance local adaptation and global generalization for vision and language tasks. Then, we present a lightweight, convolution-based approach to time-series forecasting that pairs learnable trend/seasonality decomposition with an efficient federated protocol, enabling accurate prediction across distributed, streaming signals on constrained devices. Finally, we develop adaptive federated distillation with dual adapters and instance-wise fusion, aligning shared knowledge at the server while preserving client-specific representations to improve personalization under non-IID data. Together, these contributions chart a cohesive path toward scalable, resource-aware, and personalization friendly federated learning across data types and tasks, closing the gap between theoretical promise and deployment reality while maintaining user privacy."]},{"key":"dc:format.mimetype","label":"Dc Format Mimetype","values":["PDF"]},{"key":"dc:title","label":"Title","values":["Communication-efficient personalization in federated learning for edge devices"]}]}],"canonical_facts":{"dc:contributor.advisor":["Jannesari, Ali","Basu, Samik","Huang, Xiaoqiu","Zhang, Wensheng","Gao, Hongyang"],"dc:contributor.department":["Department of Computer Science"],"dc:creator":["Nguyen, Duy Phuong"],"dc:date.accessioned":["2026-01-29T20:16:59Z"],"dc:date.available":["2026-01-29T20:16:59Z"],"dc:date.issued":["2025-12"],"dc:description.abstract":["This dissertation advances practical, privacy-preserving federated learning under real-world constraints of heterogeneity, limited resources, and diverse data modalities. It develops algorithms that make collaborative training more efficient, robust, and personalized without centralizing data. First, we introduce a dataset-aware dynamic pruning strategy coupled with gradient control to curb overfitting on heterogeneous clients, stabilize convergence, and lower both computation and communication during local updates. Next, we propose a multimodal federated framework with dual adapters: one larger adapter that is private to each client for personalization and a compact, shared adapter for knowledge transfer, augmented with selective pruning to balance local adaptation and global generalization for vision and language tasks. Then, we present a lightweight, convolution-based approach to time-series forecasting that pairs learnable trend/seasonality decomposition with an efficient federated protocol, enabling accurate prediction across distributed, streaming signals on constrained devices. Finally, we develop adaptive federated distillation with dual adapters and instance-wise fusion, aligning shared knowledge at the server while preserving client-specific representations to improve personalization under non-IID data. Together, these contributions chart a cohesive path toward scalable, resource-aware, and personalization friendly federated learning across data types and tasks, closing the gap between theoretical promise and deployment reality while maintaining user privacy."],"dc:format.mimetype":["PDF"],"dc:identifier.doi":["https://doi.org/10.31274/td-20260223-50"],"dc:identifier.uri":["https://dr.lib.iastate.edu/handle/20.500.12876/1wgeg5lr"],"dc:language.iso":["en"],"dc:title":["Communication-efficient personalization in federated learning for edge devices"],"dc:type":["dissertation"],"thesis:degree_discipline":["Engineering"],"thesis:degree_level":["dissertation"],"thesis:degree_name":["Doctor of Philosophy"],"thesis:institution_name":["Iowa State University"]},"updated_at":"2026-07-24T02:37:16Z"}